[PATCH v2 01/16] block: Add atomic write operations to request_queue limits

[John Garry <john.g.garry@oracle.com>]

From: Himanshu Madhani <himanshu.madhani@oracle.com>

Add the following limits:
- atomic_write_boundary_bytes
- atomic_write_max_bytes
- atomic_write_unit_max_bytes
- atomic_write_unit_min_bytes

All atomic writes limits are initialised to 0 to indicate no atomic write
support. Stacked devices are just not supported either for now.

Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com>
#jpg: Heavy rewrite
Signed-off-by: John Garry <john.g.garry@oracle.com>
---
 Documentation/ABI/stable/sysfs-block | 47 ++++++++++++++++++++++
 block/blk-settings.c                 | 60 ++++++++++++++++++++++++++++
 block/blk-sysfs.c                    | 33 +++++++++++++++
 include/linux/blkdev.h               | 37 +++++++++++++++++
 4 files changed, 177 insertions(+)

diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block
index 1fe9a553c37b..ba81a081522f 100644
--- a/Documentation/ABI/stable/sysfs-block
+++ b/Documentation/ABI/stable/sysfs-block
@@ -21,6 +21,53 @@ Description:
 		device is offset from the internal allocation unit's
 		natural alignment.
 
+What:		/sys/block/<disk>/atomic_write_max_bytes
+Date:		May 2023
+Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>
+Description:
+		[RO] This parameter specifies the maximum atomic write
+		size reported by the device. This parameter is relevant
+		for merging of writes, where a merged atomic write
+		operation must not exceed this number of bytes.
+		The atomic_write_max_bytes may exceed the value in
+		atomic_write_unit_max_bytes if atomic_write_max_bytes
+		is not a power-of-two or atomic_write_unit_max_bytes is
+		limited by some queue limits, such as max_segments.
+
+
+What:		/sys/block/<disk>/atomic_write_unit_min_bytes
+Date:		May 2023
+Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>
+Description:
+		[RO] This parameter specifies the smallest block which can
+		be written atomically with an atomic write operation. All
+		atomic write operations must begin at a
+		atomic_write_unit_min boundary and must be multiples of
+		atomic_write_unit_min. This value must be a power-of-two.
+
+
+What:		/sys/block/<disk>/atomic_write_unit_max_bytes
+Date:		January 2023
+Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>
+Description:
+		[RO] This parameter defines the largest block which can be
+		written atomically with an atomic write operation. This
+		value must be a multiple of atomic_write_unit_min and must
+		be a power-of-two.
+
+
+What:		/sys/block/<disk>/atomic_write_boundary_bytes
+Date:		May 2023
+Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>
+Description:
+		[RO] A device may need to internally split I/Os which
+		straddle a given logical block address boundary. In that
+		case a single atomic write operation will be processed as
+		one of more sub-operations which each complete atomically.
+		This parameter specifies the size in bytes of the atomic
+		boundary if one is reported by the device. This value must
+		be a power-of-two.
+
 
 What:		/sys/block/<disk>/diskseq
 Date:		February 2021
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 0046b447268f..d151be394c98 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -59,6 +59,10 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->zoned = BLK_ZONED_NONE;
 	lim->zone_write_granularity = 0;
 	lim->dma_alignment = 511;
+	lim->atomic_write_unit_min_sectors = 0;
+	lim->atomic_write_unit_max_sectors = 0;
+	lim->atomic_write_max_sectors = 0;
+	lim->atomic_write_boundary_sectors = 0;
 }
 
 /**
@@ -183,6 +187,62 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
+/**
+ * blk_queue_atomic_write_max_bytes - set max bytes supported by
+ * the device for atomic write operations.
+ * @q:  the request queue for the device
+ * @size: maximum bytes supported
+ */
+void blk_queue_atomic_write_max_bytes(struct request_queue *q,
+				      unsigned int bytes)
+{
+	q->limits.atomic_write_max_sectors = bytes >> SECTOR_SHIFT;
+}
+EXPORT_SYMBOL(blk_queue_atomic_write_max_bytes);
+
+/**
+ * blk_queue_atomic_write_boundary_bytes - Device's logical block address space
+ * which an atomic write should not cross.
+ * @q:  the request queue for the device
+ * @bytes: must be a power-of-two.
+ */
+void blk_queue_atomic_write_boundary_bytes(struct request_queue *q,
+					   unsigned int bytes)
+{
+	q->limits.atomic_write_boundary_sectors = bytes >> SECTOR_SHIFT;
+}
+EXPORT_SYMBOL(blk_queue_atomic_write_boundary_bytes);
+
+/**
+ * blk_queue_atomic_write_unit_min_sectors - smallest unit that can be written
+ * atomically to the device.
+ * @q:  the request queue for the device
+ * @sectors: must be a power-of-two.
+ */
+void blk_queue_atomic_write_unit_min_sectors(struct request_queue *q,
+					     unsigned int sectors)
+{
+	struct queue_limits *limits = &q->limits;
+
+	limits->atomic_write_unit_min_sectors = sectors;
+}
+EXPORT_SYMBOL(blk_queue_atomic_write_unit_min_sectors);
+
+/*
+ * blk_queue_atomic_write_unit_max_sectors - largest unit that can be written
+ * atomically to the device.
+ * @q: the request queue for the device
+ * @sectors: must be a power-of-two.
+ */
+void blk_queue_atomic_write_unit_max_sectors(struct request_queue *q,
+					     unsigned int sectors)
+{
+	struct queue_limits *limits = &q->limits;
+
+	limits->atomic_write_unit_max_sectors = sectors;
+}
+EXPORT_SYMBOL(blk_queue_atomic_write_unit_max_sectors);
+
 /**
  * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
  * @q:  the request queue for the device
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 0b2d04766324..4ebf148cf356 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -118,6 +118,30 @@ static ssize_t queue_max_discard_segments_show(struct request_queue *q,
 	return queue_var_show(queue_max_discard_segments(q), page);
 }
 
+static ssize_t queue_atomic_write_max_bytes_show(struct request_queue *q,
+						char *page)
+{
+	return queue_var_show(queue_atomic_write_max_bytes(q), page);
+}
+
+static ssize_t queue_atomic_write_boundary_show(struct request_queue *q,
+						char *page)
+{
+	return queue_var_show(queue_atomic_write_boundary_bytes(q), page);
+}
+
+static ssize_t queue_atomic_write_unit_min_show(struct request_queue *q,
+						char *page)
+{
+	return queue_var_show(queue_atomic_write_unit_min_bytes(q), page);
+}
+
+static ssize_t queue_atomic_write_unit_max_show(struct request_queue *q,
+						char *page)
+{
+	return queue_var_show(queue_atomic_write_unit_max_bytes(q), page);
+}
+
 static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(q->limits.max_integrity_segments, page);
@@ -507,6 +531,11 @@ QUEUE_RO_ENTRY(queue_discard_max_hw, "discard_max_hw_bytes");
 QUEUE_RW_ENTRY(queue_discard_max, "discard_max_bytes");
 QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data");
 
+QUEUE_RO_ENTRY(queue_atomic_write_max_bytes, "atomic_write_max_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_boundary, "atomic_write_boundary_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes");
+
 QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes");
 QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes");
 QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes");
@@ -634,6 +663,10 @@ static struct attribute *queue_attrs[] = {
 	&queue_discard_max_entry.attr,
 	&queue_discard_max_hw_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
+	&queue_atomic_write_max_bytes_entry.attr,
+	&queue_atomic_write_boundary_entry.attr,
+	&queue_atomic_write_unit_min_entry.attr,
+	&queue_atomic_write_unit_max_entry.attr,
 	&queue_write_same_max_entry.attr,
 	&queue_write_zeroes_max_entry.attr,
 	&queue_zone_append_max_entry.attr,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 51fa7ffdee83..ab53163dd187 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -309,6 +309,11 @@ struct queue_limits {
 	unsigned int		discard_alignment;
 	unsigned int		zone_write_granularity;
 
+	unsigned int		atomic_write_boundary_sectors;
+	unsigned int		atomic_write_max_sectors;
+	unsigned int		atomic_write_unit_min_sectors;
+	unsigned int		atomic_write_unit_max_sectors;
+
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
@@ -908,6 +913,14 @@ void blk_queue_zone_write_granularity(struct request_queue *q,
 				      unsigned int size);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
+void blk_queue_atomic_write_max_bytes(struct request_queue *q,
+				unsigned int bytes);
+void blk_queue_atomic_write_unit_max_sectors(struct request_queue *q,
+				unsigned int sectors);
+void blk_queue_atomic_write_unit_min_sectors(struct request_queue *q,
+				unsigned int sectors);
+void blk_queue_atomic_write_boundary_bytes(struct request_queue *q,
+				unsigned int bytes);
 void disk_update_readahead(struct gendisk *disk);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
@@ -1312,6 +1325,30 @@ static inline int queue_dma_alignment(const struct request_queue *q)
 	return q ? q->limits.dma_alignment : 511;
 }
 
+static inline unsigned int
+queue_atomic_write_unit_max_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_unit_max_sectors << SECTOR_SHIFT;
+}
+
+static inline unsigned int
+queue_atomic_write_unit_min_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_unit_min_sectors << SECTOR_SHIFT;
+}
+
+static inline unsigned int
+queue_atomic_write_boundary_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_boundary_sectors << SECTOR_SHIFT;
+}
+
+static inline unsigned int
+queue_atomic_write_max_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_max_sectors << SECTOR_SHIFT;
+}
+
 static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
 {
 	return queue_dma_alignment(bdev_get_queue(bdev));
-- 
2.35.3